Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Security audit
物业专项维修资金使用与分摊核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local-only Chinese property-maintenance-fund checker that reads user-provided tables and performs disclosed arithmetic/format checks without network use, persistence, or hidden data handling.
Install only if you are comfortable running a local Node-based checker on Chinese maintenance-fund table data. Use it as an arithmetic and formatting aid, not as legal approval, audit, bank verification, or proof that source documents are genuine.
Vulnerability Patterns
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)
Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Lp1
High
- Category
- MCP Least Privilege
- Confidence
- 75% confidence
- Finding
- The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.
Natural-Language Policy Violations
Medium
- Confidence
- 96% confidence
- Finding
- The file’s header comments, sample data, labels, advice text, and result messages are all written in Chinese, and the parser is built around Chinese column names and outputs Chinese-only guidance. There is no indication that the user can opt into another language or that the skill is explicitly restricted to a Chinese-language/regional deployment, which creates a language-policy concern under the stated rule.
Intent-Code Divergence
Medium
- Confidence
- 89% confidence
- Finding
- The success note overstates what was verified by claiming the checks showed '表决面积与资料对得上', but the code only performs arithmetic consistency checks on values present in the submitted table and does not validate source materials or evidentiary correspondence. This can mislead users into relying on the tool as stronger validation than it actually provides, causing improper approvals or missed fraud/inconsistency in underlying documents.
Natural-Language Policy Violations
Low
- Confidence
- 93% confidence
- Finding
- Multiple comments, usage strings, error messages, and output text are hard-coded in Chinese throughout the file. Because the skill does not offer any language selection or indicate that it is intentionally limited to Chinese-speaking users, it may force a specific language without user opt-in.
Intent-Code Divergence
Low
- Confidence
- 86% confidence
- Finding
- The inline documentation states that non-JSON input will be handled as plain-text material such as a '合同全文', which contradicts the surrounding module description and help text that repeatedly limit the skill to '专项维修资金归集与使用材料（含表头）'. The implementation does indeed accept any non-JSON file as raw text, so the comment broadens the apparent intended input domain beyond the stated skill purpose.
Static analysis
No suspicious patterns detected.